Initial commit

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,70 @@
+---
+library_name: stable-baselines3
+tags:
+- Hopper-v3
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: TQC
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: Hopper-v3
+      type: Hopper-v3
+    metrics:
+    - type: mean_reward
+      value: 3644.20 +/- 5.10
+      name: mean_reward
+      verified: false
+---
+
+# **TQC** Agent playing **Hopper-v3**
+This is a trained model of a **TQC** agent playing **Hopper-v3**
+using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
+and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
+
+The RL Zoo is a training framework for Stable Baselines3
+reinforcement learning agents,
+with hyperparameter optimization and pre-trained agents included.
+
+## Usage (with SB3 RL Zoo)
+
+RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
+SB3: https://github.com/DLR-RM/stable-baselines3<br/>
+SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
+
+Install the RL Zoo (with SB3 and SB3-Contrib):
+```bash
+pip install rl_zoo3
+```
+
+```
+# Download model and save it into the logs/ folder
+python -m rl_zoo3.load_from_hub --algo tqc --env Hopper-v3 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo tqc --env Hopper-v3  -f logs/
+```
+
+If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
+```
+python -m rl_zoo3.load_from_hub --algo tqc --env Hopper-v3 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo tqc --env Hopper-v3  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo tqc --env Hopper-v3 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo tqc --env Hopper-v3 -f logs/ -orga qgallouedec
+```
+
+## Hyperparameters
+```python
+OrderedDict([('learning_starts', 10000),
+             ('n_timesteps', 1000000.0),
+             ('policy', 'MlpPolicy'),
+             ('top_quantiles_to_drop_per_net', 5),
+             ('normalize', False)])
+```

args.yml

@@ -0,0 +1,83 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - tqc
+  - - conf_file
+    - null
+  - - device
+    - auto
+  - - env
+    - Hopper-v3
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 20
+  - - eval_freq
+    - 25000
+  - - gym_packages
+    - []
+  - - hyperparams
+    - null
+  - - log_folder
+    - logs
+  - - log_interval
+    - -1
+  - - max_total_trials
+    - null
+  - - n_eval_envs
+    - 5
+  - - n_evaluations
+    - null
+  - - n_jobs
+    - 1
+  - - n_startup_trials
+    - 10
+  - - n_timesteps
+    - -1
+  - - n_trials
+    - 500
+  - - no_optim_plots
+    - false
+  - - num_threads
+    - -1
+  - - optimization_log_path
+    - null
+  - - optimize_hyperparameters
+    - false
+  - - progress
+    - false
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 2496077244
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - runs/Hopper-v3__tqc__2496077244__1675878102
+  - - track
+    - true
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1
+  - - wandb_entity
+    - openrlbenchmark
+  - - wandb_project_name
+    - sb3
+  - - wandb_tags
+    - []
+  - - yaml_file
+    - null

config.yml

@@ -0,0 +1,9 @@
+!!python/object/apply:collections.OrderedDict
+- - - learning_starts
+    - 10000
+  - - n_timesteps
+    - 1000000.0
+  - - policy
+    - MlpPolicy
+  - - top_quantiles_to_drop_per_net
+    - 5

env_kwargs.yml

@@ -0,0 +1 @@
+{}

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e194f70bfa0629973c3b6fb782d90bb267e690714fac446feee17893b288b56
+size 1461387

results.json

@@ -0,0 +1 @@
+{"mean_reward": 3644.1967211, "std_reward": 5.09874503682591, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-28T15:54:48.926356"}

tqc-Hopper-v3.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4aa66a25d1ddf2547904bd6e5811f01ead3b5559607c12c2e6155ee1b343f9a1
+size 3328139

tqc-Hopper-v3/_stable_baselines3_version

@@ -0,0 +1 @@
+1.8.0a6

tqc-Hopper-v3/actor.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72c76fc55c7c9c541f1dc5004e97ae677eadd1b1a260d8dbd73ed9b1b2af4a60
+size 569757

tqc-Hopper-v3/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:810cc6574a624c48351ad84e46c9c1043bc28e35dfe5aa88a328651b5ad2bfa3
+size 1226489

tqc-Hopper-v3/data

@@ -0,0 +1,115 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVKgAAAAAAAACMGHNiM19jb250cmliLnRxYy5wb2xpY2llc5SMCVRRQ1BvbGljeZSTlC4=",
+        "__module__": "sb3_contrib.tqc.policies",
+        "__doc__": "\n    Policy class (with both actor and critic) for TQC.\n\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param lr_schedule: Learning rate schedule (could be constant)\n    :param net_arch: The specification of the policy and value networks.\n    :param activation_fn: Activation function\n    :param use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` when using gSDE to ensure\n        a positive standard deviation (cf paper). It allows to keep variance\n        above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n    :param clip_mean: Clip the mean output when using gSDE to avoid numerical instability.\n    :param features_extractor_class: Features extractor to use.\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the feature extractor.\n    :param normalize_images: Whether to normalize images or not,\n         dividing by 255.0 (True by default)\n    :param optimizer_class: The optimizer to use,\n        ``th.optim.Adam`` by default\n    :param optimizer_kwargs: Additional keyword arguments,\n        excluding the learning rate, to pass to the optimizer\n    :param n_quantiles: Number of quantiles for the critic.\n    :param n_critics: Number of critic networks to create.\n    :param share_features_extractor: Whether to share or not the features extractor\n        between the actor and the critic (this saves computation time)\n    ",
+        "__init__": "<function TQCPolicy.__init__ at 0x7f52c8566670>",
+        "_build": "<function TQCPolicy._build at 0x7f52c8566700>",
+        "_get_constructor_parameters": "<function TQCPolicy._get_constructor_parameters at 0x7f52c8566790>",
+        "reset_noise": "<function TQCPolicy.reset_noise at 0x7f52c8566820>",
+        "make_actor": "<function TQCPolicy.make_actor at 0x7f52c85668b0>",
+        "make_critic": "<function TQCPolicy.make_critic at 0x7f52c8566940>",
+        "forward": "<function TQCPolicy.forward at 0x7f52c85669d0>",
+        "_predict": "<function TQCPolicy._predict at 0x7f52c8566a60>",
+        "set_training_mode": "<function TQCPolicy.set_training_mode at 0x7f52c8566af0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f52c8567680>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        "use_sde": false
+    },
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float64",
+        "_shape": [
+            11
+        ],
+        "low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf]",
+        "high": "[inf inf inf inf inf inf inf inf inf inf inf]",
+        "bounded_below": "[False False False False False False False False False False False]",
+        "bounded_above": "[False False False False False False False False False False False]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "_shape": [
+            3
+        ],
+        "low": "[-1. -1. -1.]",
+        "high": "[1. 1. 1.]",
+        "bounded_below": "[ True  True  True]",
+        "bounded_above": "[ True  True  True]",
+        "_np_random": "RandomState(MT19937)"
+    },
+    "n_envs": 1,
+    "num_timesteps": 1000000,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1675878107124361159,
+    "learning_rate": 0.0003,
+    "tensorboard_log": "runs/Hopper-v3__tqc__2496077244__1675878102/Hopper-v3",
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": null,
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVzQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJZYAAAAAAAAAL6ccCH9NvU/8Dqnwi0ytb+xK5YzsHbcv9qTCJPAo9O/Kd0AxTG54796JiaWQroAQGYmBpyGVQhA+nPx05P0/j/ZNdp61IYhQALrb2lPISLAAAAAAAAAJMCUjAVudW1weZSMBWR0eXBllJOUjAJmOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLC4aUjAFDlHSUUpQu"
+    },
+    "_episode_num": 2263,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": 0.0,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 990000,
+    "buffer_size": 1,
+    "batch_size": 256,
+    "learning_starts": 10000,
+    "tau": 0.005,
+    "gamma": 0.99,
+    "gradient_steps": 1,
+    "optimize_memory_usage": false,
+    "replay_buffer_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==",
+        "__module__": "stable_baselines3.common.buffers",
+        "__doc__": "\n    Replay buffer used in off-policy algorithms like SAC/TD3.\n\n    :param buffer_size: Max number of element in the buffer\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param device: PyTorch device\n    :param n_envs: Number of parallel environments\n    :param optimize_memory_usage: Enable a memory efficient variant\n        of the replay buffer which reduces by almost a factor two the memory used,\n        at a cost of more complexity.\n        See https://github.com/DLR-RM/stable-baselines3/issues/37#issuecomment-637501195\n        and https://github.com/DLR-RM/stable-baselines3/pull/28#issuecomment-637559274\n        Cannot be used in combination with handle_timeout_termination.\n    :param handle_timeout_termination: Handle timeout termination (due to timelimit)\n        separately and treat the task as infinite horizon task.\n        https://github.com/DLR-RM/stable-baselines3/issues/284\n    ",
+        "__init__": "<function ReplayBuffer.__init__ at 0x7f52c89ee5e0>",
+        "add": "<function ReplayBuffer.add at 0x7f52c89ee670>",
+        "sample": "<function ReplayBuffer.sample at 0x7f52c89ee700>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7f52c89ee790>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f52c89e6a00>"
+    },
+    "replay_buffer_kwargs": {},
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
+    },
+    "use_sde_at_warmup": false,
+    "target_entropy": -3.0,
+    "ent_coef": "auto",
+    "target_update_interval": 1,
+    "top_quantiles_to_drop_per_net": 5,
+    "batch_norm_stats": [],
+    "batch_norm_stats_target": []
+}

tqc-Hopper-v3/ent_coef_optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fda0af0bcc365167bd78d8c37090c2a4bab93808a7f4c30701cb335ee8927a23
+size 1507

tqc-Hopper-v3/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e038add0ca91540e615b3aaca53855c9f273772c27dd62cb02de3813ccb83b7
+size 1509381

tqc-Hopper-v3/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8369c15cac70051c68153f2077c94e03501fe4f1301157738ba2ee72c6b5168d
+size 747

tqc-Hopper-v3/system_info.txt

@@ -0,0 +1,7 @@
+- OS: Linux-5.19.0-32-generic-x86_64-with-glibc2.35 # 33~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Mon Jan 30 17:03:34 UTC 2
+- Python: 3.9.12
+- Stable-Baselines3: 1.8.0a6
+- PyTorch: 1.13.1+cu117
+- GPU Enabled: True
+- Numpy: 1.24.1
+- Gym: 0.21.0

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a8f609863323e1b4b949186030a9e81e806191f41a95f4ac9c6edc6df1d67b8
+size 76720